Related papers: Higher-Order Modular Attention: Fusing Pairwise an…

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Multimodal sentiment analysis utilizes multiple heterogeneous modalities for sentiment classification. The recent multimodal fusion schemes customize LSTMs to discover intra-modal dynamics and design sophisticated attention mechanisms to…

Efficient modeling of long sequences of high-order data requires a more efficient architecture than Transformer. In this paper, we investigate two key aspects of extending linear recurrent models, especially those originally designed for…

The prediction of protein interactions (CPIs) is crucial for the in-silico screening step in drug discovery. Recently, many end-to-end representation learning methods using deep neural networks have achieved significantly better performance…

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

This paper presents LAPA (Look Around and Pay Attention), a novel end-to-end transformer-based architecture for multi-camera point tracking that integrates appearance-based matching with geometric constraints. Traditional pipelines decouple…

Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point…

Multimodal Transformers serve as the backbone for state-of-the-art vision-language models, yet their quadratic attention complexity remains a critical barrier to scalability. In this work, we investigate the viability of Linear Attention…

Predicting the behaviors of other agents on the road is critical for autonomous driving to ensure safety and efficiency. However, the challenging part is how to represent the social interactions between agents and output different possible…

Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a…

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

Aggregating multi-modality data to obtain reliable data representation attracts more and more attention. Recent studies demonstrate that Transformer models usually work well for multi-modality tasks. Existing Transformers generally either…

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by…

Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT evaluation metric, HOTA (Higher Order Tracking…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Recently, large pre-trained neural language models have attained remarkable performance on many downstream natural language processing (NLP) applications via fine-tuning. In this paper, we target at how to further improve the token…

Human-object interaction (HOI) detection is an important part of understanding human activities and visual scenes. The long-tailed distribution of labeled instances is a primary challenge in HOI detection, promoting research in few-shot and…

Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism concerning the sequence length. This…

Geometric Attention (GA) specifies an attention layer by four independent inputs: a finite carrier (what indices are addressable), an evidence-kernel rule (how masked proto-scores and a link induce nonnegative weights), a probe family…